Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 994 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2501. Min Act: -0.0003

Data Index: 1144366 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2343. Min Act: -0.0003

Data Index: 322427 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2256. Min Act: -0.0003

Data Index: 728966 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2217. Min Act: -0.0003

Data Index: 438708 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2204. Min Act: -0.0003

Data Index: 1191622 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2186. Min Act: -0.0003

Data Index: 356227 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2248. Min Act: -0.0003

Data Index: 663771 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2162. Min Act: -0.0003

Data Index: 293005 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2129. Min Act: -0.0003

Data Index: 363206 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2129. Min Act: -0.0003

Data Index: 596517 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2150. Min Act: -0.0003

Data Index: 1088776 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2005. Min Act: -0.0003

Data Index: 996672 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1956. Min Act: -0.0003

Data Index: 1066525 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2019. Min Act: -0.0003

Data Index: 1233146 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2093. Min Act: -0.0003

Data Index: 478177 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2015. Min Act: -0.0003

Data Index: 677819 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2005. Min Act: -0.0003

Data Index: 404944 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1994. Min Act: -0.0003

Data Index: 1117875 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1853. Min Act: -0.0003

Data Index: 490386 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2130. Min Act: -0.0003

Data Index: 475576 (C4 (Web Text))

Max Activating Token Index: 309